CAlphabet类 参考

详细描述

The class Alphabet implements an alphabet and alphabet utility functions.

These utility functions can be used to remap characters to more (bit-)efficient representations, check if a string is valid, compute histograms etc.

Currently supported alphabets are DNA, RAWDNA, RNA, PROTEIN, BINARY, ALPHANUM, CUBE, RAW, IUPAC_NUCLEIC_ACID and IUPAC_AMINO_ACID.

在文件 Alphabet.h 第 91 行定义.

类 CAlphabet 继承关系图:

Public 成员函数
	CAlphabet ()
	CAlphabet (char *alpha, int32_t len)
	CAlphabet (EAlphabet alpha)
	CAlphabet (CAlphabet *alpha)
virtual	~CAlphabet ()
bool	set_alphabet (EAlphabet alpha)
EAlphabet	get_alphabet () const
int32_t	get_num_symbols () const
int32_t	get_num_bits () const
uint8_t	remap_to_bin (uint8_t c)
uint8_t	remap_to_char (uint8_t c)
void	clear_histogram ()
	clear histogram 更多...
template<class T >
void	add_string_to_histogram (T *p, int64_t len)
void	add_byte_to_histogram (uint8_t p)
void	print_histogram ()
	print histogram 更多...
SGVector< int64_t >	get_histogram ()
bool	check_alphabet (bool print_error=true)
bool	is_valid (uint8_t c)
bool	check_alphabet_size (bool print_error=true)
int32_t	get_num_symbols_in_histogram ()
int32_t	get_max_value_in_histogram ()
int32_t	get_num_bits_in_histogram ()
virtual const char *	get_name () const
template<>
void	translate_from_single_order (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
virtual CSGObject *	shallow_copy () const
virtual CSGObject *	deep_copy () const
virtual bool	is_generic (EPrimitiveType *generic) const
template<class T >
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
template<>
void	set_generic ()
void	unset_generic ()
virtual void	print_serializable (const char *prefix="")
virtual bool	save_serializable (CSerializableFile *file, const char *prefix="")
virtual bool	load_serializable (CSerializableFile *file, const char *prefix="")
void	set_global_io (SGIO *io)
SGIO *	get_global_io ()
void	set_global_parallel (Parallel *parallel)
Parallel *	get_global_parallel ()
void	set_global_version (Version *version)
Version *	get_global_version ()
SGStringList< char >	get_modelsel_names ()
void	print_modsel_params ()
char *	get_modsel_param_descr (const char *param_name)
index_t	get_modsel_param_index (const char *param_name)
void	build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict)
virtual void	update_parameter_hash ()
virtual bool	parameter_hash_changed ()
virtual bool	equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)
virtual CSGObject *	clone ()

静态 Public 成员函数
static const char *	get_alphabet_name (EAlphabet alphabet)
template<class ST >
static void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
template<class ST >
static void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
template<class ST >
static void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<class ST >
static void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)

Public 属性
SGIO *	io
Parallel *	parallel
Version *	version
Parameter *	m_parameters
Parameter *	m_model_selection_parameters
Parameter *	m_gradient_parameters
uint32_t	m_hash

静态 Public 属性
static const uint8_t	B_A =0
static const uint8_t	B_C =1
static const uint8_t	B_G =2
static const uint8_t	B_T =3
static const uint8_t	B_0 =4
static const uint8_t	MAPTABLE_UNDEF =0xff
static const char *	alphabet_names [18]

Protected 成员函数
void	init_map_table ()
void	copy_histogram (CAlphabet *src)
virtual void	load_serializable_post () throw (ShogunException)
virtual void	load_serializable_pre () throw (ShogunException)
virtual void	save_serializable_pre () throw (ShogunException)
virtual void	save_serializable_post () throw (ShogunException)

Protected 属性
EAlphabet	alphabet
int32_t	num_symbols
int32_t	num_bits
bool	valid_chars [1<< (sizeof(uint8_t)*8)]
uint8_t	maptable_to_bin [1<< (sizeof(uint8_t)*8)]
uint8_t	maptable_to_char [1<< (sizeof(uint8_t)*8)]
int64_t	histogram [1<< (sizeof(uint8_t)*8)]

构造及析构函数说明

CAlphabet

(

)

default constructor

在文件 Alphabet.cpp 第 35 行定义.

CAlphabet	(	char *	alpha,
		int32_t	len
	)

constructor

参数

alpha	alphabet to use
len	len

在文件 Alphabet.cpp 第 41 行定义.

CAlphabet

(

EAlphabet

alpha

)

constructor

参数

alpha

alphabet (type) to use

在文件 Alphabet.cpp 第 88 行定义.

CAlphabet

(

CAlphabet *

alpha

)

constructor

参数

alpha

alphabet to use

在文件 Alphabet.cpp 第 95 行定义.

~CAlphabet ( )

virtual

在文件 Alphabet.cpp 第 104 行定义.

成员函数说明

void add_byte_to_histogram

(

uint8_t

p

)

add element to histogram

参数

p

element

在文件 Alphabet.h 第 193 行定义.

void add_string_to_histogram	(	T *	p,
		int64_t	len
	)

make histogram for whole string

参数

p	string
len	length of string

在文件 Alphabet.h 第 183 行定义.

void build_gradient_parameter_dictionary ( CMap< TParameter *, CSGObject * > *  dict )

inherited

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

参数

dict	dictionary of parameters to be built.

在文件 SGObject.cpp 第 597 行定义.

bool check_alphabet

(

bool

print_error = true

)

check whether symbols in histogram are valid in alphabet e.g. for DNA if only letters ACGT appear

参数

print_error

if errors shall be printed

返回

if symbols in histogram are valid in alphabet

在文件 Alphabet.cpp 第 617 行定义.

bool check_alphabet_size

(

bool

print_error = true

)

check whether symbols in histogram ALL fit in alphabet

参数

print_error

if errors shall be printed

返回

if symbols in histogram ALL fit in alphabet

在文件 Alphabet.cpp 第 639 行定义.

void clear_histogram

(

)

clear histogram

在文件 Alphabet.cpp 第 544 行定义.

CSGObject * clone ( )

virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

返回

an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

在文件 SGObject.cpp 第 714 行定义.

void copy_histogram ( CAlphabet *  src )

protected

copy histogram

参数

src	alphabet to copy histogram from

在文件 Alphabet.cpp 第 656 行定义.

CSGObject * deep_copy ( ) const

virtualinherited

A deep copy. All the instance variables will also be copied.

在文件 SGObject.cpp 第 198 行定义.

bool equals ( CSGObject *  other, float64_t  accuracy = 0.0, bool  tolerant = false  )

virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

参数

other	object to compare with
accuracy	accuracy to use for comparison (optional)
tolerant	allows linient check on float equality (within accuracy)

返回

true if all parameters were equal, false if not

在文件 SGObject.cpp 第 618 行定义.

EAlphabet get_alphabet

(

)

const

get alphabet

返回

alphabet

在文件 Alphabet.h 第 130 行定义.

const char * get_alphabet_name ( EAlphabet  alphabet )

static

return alphabet name

参数

alphabet

alphabet type to get name from

在文件 Alphabet.cpp 第 669 行定义.

SGIO * get_global_io ( )

inherited

get the io object

返回

io object

在文件 SGObject.cpp 第 235 行定义.

Parallel * get_global_parallel ( )

inherited

get the parallel object

返回

parallel object

在文件 SGObject.cpp 第 277 行定义.

Version * get_global_version ( )

inherited

get the version object

返回

version object

在文件 SGObject.cpp 第 290 行定义.

SGVector< int64_t > get_histogram

(

)

get histogram

返回

histogram

在文件 Alphabet.cpp 第 612 行定义.

int32_t get_max_value_in_histogram

(

)

return maximum value in histogram

返回

maximum value in histogram

在文件 Alphabet.cpp 第 550 行定义.

SGStringList< char > get_modelsel_names ( )

inherited

返回

vector of names of all parameters which are registered for model selection

在文件 SGObject.cpp 第 498 行定义.

char * get_modsel_param_descr ( const char *  param_name )

inherited

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

参数

param_name

name of the parameter

返回

description of the parameter

在文件 SGObject.cpp 第 522 行定义.

index_t get_modsel_param_index ( const char *  param_name )

inherited

Returns index of model selection parameter with provided index

参数

param_name

name of model selection parameter

返回

index of model selection parameter with provided name, -1 if there is no such

在文件 SGObject.cpp 第 535 行定义.

virtual const char* get_name ( ) const

virtual

返回

object name

实现了 CSGObject.

在文件 Alphabet.h 第 261 行定义.

int32_t get_num_bits

(

)

const

get number of bits necessary to store all symbols in alphabet

返回

number of necessary storage bits

在文件 Alphabet.h 第 149 行定义.

int32_t get_num_bits_in_histogram

(

)

return number of bits required to store all symbols in histogram

返回

number of bits required to store all symbols in histogram

在文件 Alphabet.cpp 第 577 行定义.

int32_t get_num_symbols

(

)

const

get number of symbols in alphabet

返回

number of symbols

在文件 Alphabet.h 第 139 行定义.

int32_t get_num_symbols_in_histogram

(

)

return number of symbols in histogram

返回

number of symbols in histogram

在文件 Alphabet.cpp 第 565 行定义.

void init_map_table ( )

protected

init map table

在文件 Alphabet.cpp 第 179 行定义.

bool is_generic ( EPrimitiveType *  generic ) const

virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

参数

generic

set to the type of the generic if returning TRUE

返回

TRUE if a class template.

在文件 SGObject.cpp 第 296 行定义.

bool is_valid

(

uint8_t

c

)

check whether symbols are valid in alphabet e.g. for DNA if symbol is one of the A,C,G or T

参数

c

symbol

返回

if symbol is a valid character in alphabet

在文件 Alphabet.h 第 221 行定义.

bool load_serializable ( CSerializableFile *  file, const char *  prefix = ""  )

virtualinherited

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

参数

file	where to load from
prefix	prefix for members

返回

TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 369 行定义.

void load_serializable_post ( ) throw ( ShogunException )

protectedvirtual

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

异常

ShogunException

Will be thrown if an error occurres.

重载 CSGObject .

在文件 Alphabet.cpp 第 749 行定义.

void load_serializable_pre ( ) throw ( ShogunException )

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

异常

ShogunException

will be thrown if an error occurs.

被 CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 421 行定义.

bool parameter_hash_changed ( )

virtualinherited

返回

whether parameter combination has changed since last update

在文件 SGObject.cpp 第 262 行定义.

void print_histogram

(

)

print histogram

在文件 Alphabet.cpp 第 587 行定义.

void print_modsel_params ( )

inherited

prints all parameter registered for model selection and their type

在文件 SGObject.cpp 第 474 行定义.

void print_serializable ( const char *  prefix = "" )

virtualinherited

prints registered parameters out

参数

prefix

prefix for members

在文件 SGObject.cpp 第 308 行定义.

uint8_t remap_to_bin

(

uint8_t

c

)

remap element e.g translate ACGT to 0123

参数

c	element to remap

返回

remapped element

在文件 Alphabet.h 第 159 行定义.

uint8_t remap_to_char

(

uint8_t

c

)

remap element e.g translate 0123 to ACGT

参数

c	element to remap

返回

remapped element

在文件 Alphabet.h 第 169 行定义.

bool save_serializable ( CSerializableFile *  file, const char *  prefix = ""  )

virtualinherited

Save this object to file.

参数

file	where to save the object; will be closed during returning if PREFIX is an empty string.
prefix	prefix for members

返回

TRUE if done, otherwise FALSE

在文件 SGObject.cpp 第 314 行定义.

void save_serializable_post ( ) throw ( ShogunException )

protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

异常

ShogunException

will be thrown if an error occurs.

被 CKernel 重载.

在文件 SGObject.cpp 第 436 行定义.

void save_serializable_pre ( ) throw ( ShogunException )

protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

异常

ShogunException

will be thrown if an error occurs.

被 CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool > , 以及 CDynamicObjectArray 重载.

在文件 SGObject.cpp 第 431 行定义.

bool set_alphabet

(

EAlphabet

alpha

)

set alphabet and initialize mapping table (for remap)

参数

alpha

new alphabet

在文件 Alphabet.cpp 第 108 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 41 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 46 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 51 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 56 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 61 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 66 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 71 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 76 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 81 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 86 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 91 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 96 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 101 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 106 行定义.

void set_generic ( )

inherited

在文件 SGObject.cpp 第 111 行定义.

void set_generic ( )

inherited

set generic type to T

void set_global_io ( SGIO *  io )

inherited

set the io object

参数

io	io object to use

在文件 SGObject.cpp 第 228 行定义.

void set_global_parallel ( Parallel *  parallel )

inherited

set the parallel object

参数

parallel

parallel object to use

在文件 SGObject.cpp 第 241 行定义.

void set_global_version ( Version *  version )

inherited

set the version object

参数

version

version object to use

在文件 SGObject.cpp 第 283 行定义.

CSGObject * shallow_copy ( ) const

virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

被 CGaussianKernel 重载.

在文件 SGObject.cpp 第 192 行定义.

void translate_from_single_order ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val  )

static

translate from single order

参数

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value

在文件 Alphabet.cpp 第 760 行定义.

void translate_from_single_order ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val, int32_t  gap  )

static

translate from single order

参数

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value
gap	gap

在文件 Alphabet.cpp 第 836 行定义.

void translate_from_single_order	(	float32_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 955 行定义.

void translate_from_single_order	(	float64_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 959 行定义.

void translate_from_single_order	(	floatmax_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 963 行定义.

void translate_from_single_order_reversed ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val  )

static

translate from single order reversed

参数

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value

在文件 Alphabet.cpp 第 798 行定义.

void translate_from_single_order_reversed ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val, int32_t  gap  )

static

translate from single order reversed

参数

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value
gap	gap

在文件 Alphabet.cpp 第 898 行定义.

void translate_from_single_order_reversed	(	float32_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 967 行定义.

void translate_from_single_order_reversed	(	float64_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 971 行定义.

void translate_from_single_order_reversed	(	floatmax_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

在文件 Alphabet.cpp 第 975 行定义.

void unset_generic ( )

inherited

unset generic type

this has to be called in classes specializing a template class

在文件 SGObject.cpp 第 303 行定义.

void update_parameter_hash ( )

virtualinherited

Updates the hash of current parameter combination

在文件 SGObject.cpp 第 248 行定义.

类成员变量说明

EAlphabet alphabet

protected

alphabet

在文件 Alphabet.h 第 353 行定义.

const char * alphabet_names

static

初始值:

={
    "DNA","RAWDNA", "RNA", "PROTEIN", "BINARY", "ALPHANUM",
    "CUBE", "RAW", "IUPAC_NUCLEIC_ACID", "IUPAC_AMINO_ACID",
    "NONE", "DIGIT", "DIGIT2", "RAWDIGIT", "RAWDIGIT2", "UNKNOWN",
    "SNP", "RAWSNP"}

alphabet names

在文件 Alphabet.h 第 338 行定义.

const uint8_t B_0 =4

static

B_0

在文件 Alphabet.h 第 334 行定义.

const uint8_t B_A =0

static

B_A

在文件 Alphabet.h 第 326 行定义.

const uint8_t B_C =1

static

B_C

在文件 Alphabet.h 第 328 行定义.

const uint8_t B_G =2

static

B_G

在文件 Alphabet.h 第 330 行定义.

const uint8_t B_T =3

static

B_T

在文件 Alphabet.h 第 332 行定义.

int64_t histogram[1<< (sizeof(uint8_t)*8)]

protected

histogram

在文件 Alphabet.h 第 365 行定义.

SGIO* io

inherited

io

在文件 SGObject.h 第 369 行定义.

Parameter* m_gradient_parameters

inherited

parameters wrt which we can compute gradients

在文件 SGObject.h 第 384 行定义.

uint32_t m_hash

inherited

Hash of parameter values

在文件 SGObject.h 第 387 行定义.

Parameter* m_model_selection_parameters

inherited

model selection parameters

在文件 SGObject.h 第 381 行定义.

Parameter* m_parameters

inherited

parameters

在文件 SGObject.h 第 378 行定义.

uint8_t maptable_to_bin[1<< (sizeof(uint8_t)*8)]

protected

maptable to bin

在文件 Alphabet.h 第 361 行定义.

uint8_t maptable_to_char[1<< (sizeof(uint8_t)*8)]

protected

maptable to char

在文件 Alphabet.h 第 363 行定义.

const uint8_t MAPTABLE_UNDEF =0xff

static

MAPTABLE UNDEF

在文件 Alphabet.h 第 336 行定义.

int32_t num_bits

protected

number of bits

在文件 Alphabet.h 第 357 行定义.

int32_t num_symbols

protected

number of symbols

在文件 Alphabet.h 第 355 行定义.

Parallel* parallel

inherited

parallel

在文件 SGObject.h 第 372 行定义.

bool valid_chars[1<< (sizeof(uint8_t)*8)]

protected

valid chars

在文件 Alphabet.h 第 359 行定义.

Version* version

inherited

version

在文件 SGObject.h 第 375 行定义.

---

该类的文档由以下文件生成:

• Alphabet.h
• Alphabet.cpp